bhavitvyamalik commited on
Commit
4461a3b
1 Parent(s): 34268b3

Upload model

Browse files
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - adapter-transformers
4
+ - adapterhub:nli/multinli
5
+ - bert
6
+ datasets:
7
+ - multi_nli
8
+ ---
9
+
10
+ # Adapter `domadapter/joint_dt_slate_telephone` for bert-base-uncased
11
+
12
+ An [adapter](https://adapterhub.ml) for the `bert-base-uncased` model that was trained on the [nli/multinli](https://adapterhub.ml/explore/nli/multinli/) dataset and includes a prediction head for classification.
13
+
14
+ This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
15
+
16
+ ## Usage
17
+
18
+ First, install `adapter-transformers`:
19
+
20
+ ```
21
+ pip install -U adapter-transformers
22
+ ```
23
+ _Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
24
+
25
+ Now, the adapter can be loaded and activated like this:
26
+
27
+ ```python
28
+ from transformers import AutoAdapterModel
29
+
30
+ model = AutoAdapterModel.from_pretrained("bert-base-uncased")
31
+ adapter_name = model.load_adapter("domadapter/joint_dt_slate_telephone", source="hf", set_active=True)
32
+ ```
33
+
34
+ ## Architecture & Training
35
+
36
+ <!-- Add some description here -->
37
+
38
+ ## Evaluation results
39
+
40
+ <!-- Add some description here -->
41
+
42
+ ## Citation
43
+
44
+ <!-- Add some description here -->
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "factorized_phm_W": true,
6
+ "factorized_phm_rule": false,
7
+ "hypercomplex_nonlinearity": "glorot-uniform",
8
+ "init_weights": "bert",
9
+ "inv_adapter": null,
10
+ "inv_adapter_reduction_factor": null,
11
+ "is_parallel": false,
12
+ "learn_phm": true,
13
+ "leave_out": [],
14
+ "ln_after": false,
15
+ "ln_before": false,
16
+ "mh_adapter": false,
17
+ "non_linearity": "relu",
18
+ "original_ln_after": true,
19
+ "original_ln_before": true,
20
+ "output_adapter": true,
21
+ "phm_bias": true,
22
+ "phm_c_init": "normal",
23
+ "phm_dim": 4,
24
+ "phm_init_range": 0.0001,
25
+ "phm_layer": false,
26
+ "phm_rank": 1,
27
+ "reduction_factor": 16,
28
+ "residual_before_ln": true,
29
+ "scaling": 1.0,
30
+ "shared_W_phm": false,
31
+ "shared_phm_rule": true,
32
+ "use_gating": false
33
+ },
34
+ "hidden_size": 768,
35
+ "model_class": "BertModelWithHeads",
36
+ "model_name": "bert-base-uncased",
37
+ "model_type": "bert",
38
+ "name": "adapter_slate_telephone",
39
+ "version": "3.2.0a0"
40
+ }
head_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "activation_function": "tanh",
4
+ "bias": true,
5
+ "head_type": "classification",
6
+ "label2id": {
7
+ "LABEL_0": 0,
8
+ "LABEL_1": 1,
9
+ "LABEL_2": 2
10
+ },
11
+ "layers": 2,
12
+ "num_labels": 3,
13
+ "use_pooler": false
14
+ },
15
+ "hidden_size": 768,
16
+ "model_class": "BertModelWithHeads",
17
+ "model_name": "bert-base-uncased",
18
+ "model_type": "bert",
19
+ "name": "adapter_slate_telephone",
20
+ "version": "3.2.0a0"
21
+ }
pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6a1cbdd8d428b7899d51bd51356fd5fef3c222318a3fc9fb1513a6e1d180f0
3
+ size 3594197
pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fed262cfa1d88ef8f926efabfe9282a5e9acb6bec90fd6424961a3eafad880f
3
+ size 2373023